INDEX
    Explanations

    references to customer service or professional behavior

    New Auto-Interp
    Negative Logits
    AnimationsModule
    -0.83
    setupUi
    -0.78
     Вікіпе
    -0.74
    Demografie
    -0.67
     ThemeData
    -0.65
    Obrázky
    -0.65
     createSprite
    -0.65
     Yoruba
    -0.63
     OMIT
    -0.63
    BagLayout
    -0.63
    POSITIVE LOGITS
     polish
    0.65
     Friendly
    0.62
    tic
    0.61
     friendly
    0.60
     Johnston
    0.59
    OLOG
    0.55
    cz
    0.54
     poli
    0.54
    friendly
    0.53
     Fie
    0.53
    Act Density 3.183%

    No Known Activations